INDEX

Explanations

numbers related to quantities or measurements

oai_token-act-pair · gpt-3.5-turbo

quantitative statistics or numerical data

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rolet

-0.66

med

-0.64

ilic

-0.64

atown

-0.63

ffen

-0.61

Reviewer

-0.61

actionDate

-0.60

ques

-0.60

amaru

-0.60

 Cutter

-0.58

POSITIVE LOGITS

1.10

1.01

1.00

0.99

0.98

0.96

Activations Density 0.239%

numbers related to quantities or measurements

quantitative statistics or numerical data

No Comments

No Known Activations